Last decades, rolling bearing faults assessment and their evolution with time have been receiving much interest due to their crucial role as part of the Conditional Based Maintenance (CBM) of rotating machinery. This paper investigates bearing faults diagnosis based on classification approach using Gaussian Mixture Model (GMM) and the Mel Frequency Cepstral Coefficients (MFCC) features. Throughout, only one criterion is defined for the evaluation of the performance during all the cycle of the classification process. This is the Average Classification Rate (ACR) obtained from the confusion matrix. In every test performed, the generated features vectors are considered along to discriminate between four fault conditions as normal bearings, bearings with inner and outer race faults and ball faults. Many configurations were tested in order to determinate the optimal values of input parameters, as the frame analysis length, the order of model, and others. The experimental application of the proposed method was based on vibration signals taken from the bearing datacenter website of Case Western Reserve University (CWRU). Results show that proposed method can reliably classify different fault conditions and have a highest classification performance under some conditions.
The rolling bearings’ diagnosing methods used in exploitation diagnostics are not usually dedicated to the postproduction control. However, this does not mean, that they cannot be used there. A comprehensive comparison of the sensitivity of rolling bearings’ diagnosing methods to occurrence of faults and damage should be based on measurements of new, undamaged bearings and bearings with defects. An accurate determination of the location, size and origin of defects is expected from a set of testing bearings. The paper presents a comparison of three methods of damage introduction: sandblasting, pickling and spark erosion. Procedures for introducing damage into bearing’s races have been described. In addition, race’s geometries and vibration signals generated by operating bearings were compared.
In this paper the results of Matching Pursuit (MP) Octave algorithm applied to noise, vibration and harness (NVH) diagnosis of rolling bearings are presented. For this purpose two bearings in different condition state were examined. The object of the analysis was to calculate and present which energy error values of MP algorithm give the most accuracy results for different changes in bearing structures and also how energy values spread in time-frequency domain for chosen energy error value.
4
Dostęp do pełnego tekstu na zewnętrznej witrynie WWW
W artykule przedstawiono wyniki badań prądów łożyskowych w silnikach indukcyjnych dużej mocy. Badania przeprowadzono w specjalistycznym laboratorium przemysłowym zapewniającym rozruch bezpośredni silników indukcyjnych dużej mocy z sieci o napięciu 1000 V. Przedstawiono uszkodzenia łożysk pod wpływem prądów łożyskowych. Udowodniono, że podczas pracy silnika występują pewne zakresy temperatur i prędkości obrotowych, w których występują niebezpieczne dla łożysk impulsy prądu łożyskowego. Przedstawione wyniki badań naświetlają zagrożenia dla trwałości węzłów łożyskowych silnika oraz obciążenia.
EN
Results of investigating bearing currents in high power induction motors are presented in the paper. The tests have been carried out in specialized industrial laboratory, where it is possible to achieve direct start of high-power induction motors supplied from 1000 V network. The bearing damages due to bearing currents are demonstrated. It has been proven that when motor operates within definite range of temperature and rotational speed, impulses of bearing currents dangerous to the bearings appear. The presented research results describe damage hazard to durability of motor and load bearing units.
JavaScript jest wyłączony w Twojej przeglądarce internetowej. Włącz go, a następnie odśwież stronę, aby móc w pełni z niej korzystać.